emergent-misalignment / emergent-misalignmentLinks
☆216Updated 7 months ago
Alternatives and similar repositories for emergent-misalignment
Users that are interested in emergent-misalignment are comparing it to the libraries listed below
Sorting:
- Open source interpretability artefacts for R1.☆161Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆204Updated 11 months ago
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models☆247Updated 2 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆278Updated 3 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated last week
- METR Task Standard☆162Updated 8 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Collection of evals for Inspect AI☆241Updated last week
- ☆142Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- Improving Alignment and Robustness with Circuit Breakers☆236Updated last year
- open source interpretability platform 🧠☆442Updated this week
- Sparsify transformers with SAEs and transcoders☆631Updated this week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆99Updated this week
- Steering Llama 2 with Contrastive Activation Addition☆187Updated last year
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆283Updated this week
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆118Updated last year
- ☆174Updated 10 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆115Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆269Updated last year
- ☆187Updated 2 months ago
- https://transformer-circuits.pub/2025/attribution-graphs/methods.html☆85Updated 6 months ago
- ☆109Updated 5 months ago
- ☆79Updated this week
- ☆54Updated 10 months ago
- ☆127Updated this week